Frequently asked questions
Who runs VoxEdge?
VoxEdge is an independent storefront for a cloud text-to-speech API. It is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. Each site in the network operates independently, providing a direct interface for developers to access the same underlying TTS engine and pricing structure without intermediary branding.
What voices are used?
We offer eight voice presets: Aria, Nova, Luna, and Sage (female); Felix, Milo, Atlas, and Orion (male). These voices support 23 languages including English, Spanish, German, and Japanese. Any voice can speak any supported language, allowing flexible configuration for diverse fintech notification requirements.
Are voices licensed?
Yes. Our voices are based on licensed recordings from LibriTTS-R (CC BY 4.0) and public-domain audiobook readings from LibriVox. This ensures clear licensing for the synthetic speech generated by our API, providing legal clarity for developers integrating audio into their banking and fintech applications.
Is data used for training?
No. Input text is used only to produce the audio and is not used for training models. Generated audio is returned in the response and not stored. Only request metadata (time, characters, status) is kept for billing purposes, ensuring privacy for your client data.
Is audio stored?
No. Generated audio is returned in the API response and is not stored on our servers. Only request metadata, such as timestamp, character count, and status, is retained for billing purposes. This minimizes data retention risks for sensitive financial notifications sent via the API.
How is data handled?
Input text is used solely to generate audio and is not used for training. Audio files are returned in the response and not stored. We retain only request metadata (time, characters, status) for billing. This ensures minimal data footprint for your fintech application's voice notifications.
Does the API support streaming?
No. The API does not support streaming, WebSocket connections, or real-time partial audio. You send text via POST request and receive the complete audio file. This synchronous model is reliable for automated notifications where immediate partial audio chunks are not required for playback.
Does the API support SSML?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. You control speech characteristics using the speed parameter (0.25–4.0) and voice selection. This simplifies integration for indie developers who need consistent, predictable audio output without managing complex markup structures.
Can I clone voices?
No. We do not offer custom voice cloning, uploading your own voice, or voice design. You choose from eight preset voices (Aria, Nova, Luna, Sage, Felix, Milo, Atlas, Orion). Each voice is based on licensed recordings, ensuring consistent quality without the complexity of custom model training.
Is there phone support?
No. There is no phone number or live chat available for support. All assistance is provided via email only.
How do I contact support?
Support is available by email only. There is no phone number or live chat. You can reach our team via the contact page or by emailing the support address provided on the site. We aim to respond to technical inquiries regarding API usage and billing promptly.
Are you affiliated with OpenAI?
No. VoxEdge is not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. While our API endpoint shape matches the OpenAI speech endpoint for easy SDK integration, we are an independent provider. Our voices, pricing, and infrastructure are entirely separate from OpenAI’s services and models.
What is the API's uptime?
There is no SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real-time, but actual latency depends on current server load and queue depth.
Who We Are
VoxEdge is an independent storefront for a cloud text-to-speech API, not a subsidiary of a larger tech brand. We operate as a standalone API provider, offering a direct path for indie developers to integrate high-quality synthetic voice into their applications without corporate overhead or complex enterprise contracts.
Our platform is built for developers who need reliability over hype. We provide a straightforward API that replaces legacy local engines with a consistent cloud service, ensuring your automated voice notifications are delivered clearly and consistently.
Independent Storefront
We are an independent storefront for the same TTS engine used across our network sites. This means you deal directly with us, without middlemen or branded overlays. Our API endpoint and authentication model remain consistent, giving you full control over your integration.
Unlike major providers, we do not bundle our service with broader ecosystems. You pay only for what you use, with transparent character-based billing and no hidden seat fees or minimum spend requirements.
- Direct API access with no ecosystem lock-in
- Transparent pricing: $10 per 1 million characters
- No monthly plans or subscription tiers
Indie Developer Focus
We design for developers who value simplicity. Our API mirrors the OpenAI request shape, so you can switch libraries easily by changing the base URL. We support standard formats like MP3 and WAV, and our documentation provides ready-to-use curl examples for immediate testing.
We understand the constraints of indie projects. With a free trial of $0.50 credit and simple USDT top-ups, you can prototype and launch without waiting for invoices or credit card approvals. Our rate limits (60 requests per minute) support most notification workflows.
- OpenAI-compatible request structure
- Simple USDT (TRC-20) top-ups
- No minimum spend or seats
Fintech Specialization
We specialize in automated voice notifications for banking and fintech apps. Our voices are clear, calm, and professional, suitable for delivering account updates, transaction alerts, and security codes. We avoid the whimsical tones that can undermine trust in financial communications.
Compliance and clarity are key. Each audio file contains an inaudible watermark marking it as synthetic speech, helping meet transparency standards. Our text processing handles up to 4096 characters per request, allowing you to send concise, compliant messages without complex splitting logic.
- Professional voices for financial alerts
- Inaudible synthetic speech watermark
- Clear, calm narration styles
Voice Licensing
VoxEdge’s synthetic voices are derived from the LibriTTS-R dataset, which captures high-quality human speech from audiobook readings. This foundation ensures natural prosody and clarity suitable for financial notifications.
The underlying recordings originate from LibriVox, a community of volunteers reading books in the public domain. This allows us to offer consistent, high-fidelity audio without relying on proprietary voice actor contracts.
LibriTTS-R Source
We use the LibriTTS-R dataset as the core training material for our voice models. This dataset provides audio segments ideal for generating clear text-to-speech output.
- High-quality single-speaker segments
- Optimized for TTS synthesis
CC BY 4.0 License
The LibriTTS-R data is released under the Creative Commons Attribution 4.0 International license. This allows us to train our models and distribute the resulting synthetic audio legally, provided you attribute the source if required by your specific use case.
Public Domain Recordings
The original audio sources are public domain audiobook readings from LibriVox volunteers. Since the underlying texts are public domain, the recordings are free of copyright restrictions, reducing legal overhead for your fintech applications.
Data Policy
When you send text to VoxEdge, our servers process it solely to generate the requested audio file. We do not use your input text to train or improve our underlying models, ensuring your proprietary notification content remains private and distinct from our dataset.
No Training Data Usage
Your input text is processed exclusively for the immediate synthesis task. Input text is used only to produce the audio and is not used for training. This ensures that your specific notification scripts, customer data, or financial messages are not used to influence future model behaviors.
No Audio Storage
Generated audio is returned in the response and not stored. This minimizes data exposure and ensures that your voice notifications are transient, existing only in your infrastructure or your user's device.
Metadata for Billing
We retain request metadata—specifically the timestamp, character count, and status—for billing accuracy. This allows us to accurately charge your balance ($0.01 per 1,000 characters) and provides a clear audit trail for your automated voice notification usage.
Technical Limits
VoxEdge delivers audio files via standard HTTP responses. We do not support WebSocket or streaming endpoints, so you receive the complete file after synthesis finishes. This simplifies integration for batch processing but requires handling full downloads for real-time playback needs.
No Streaming Support
Audio is returned as a complete file in the response body. There is no partial audio stream available during generation. For fintech notifications, this means you must wait for the full synthesis to complete before playing the audio to the user.
No SSML Support
The API accepts plain text input only. There is no support for SSML tags to control pronunciation, pauses, or emphasis. You cannot inject custom pronunciation rules or fine-tune timing within the audio generation request itself.
No Voice Cloning
We offer eight fixed presets based on licensed recordings. We do not provide custom voice cloning for customers, nor do you upload your own voice samples. Each generated file carries an inaudible watermark marking it as synthetic speech.

Support and Contact
VoxEdge is built by and for indie developers, so we prioritize clear, direct communication over complex support hierarchies. Support is by email only.
Email Support Only
All inquiries are handled exclusively through email. This single channel ensures that your question reaches the right person without navigating phone trees or waiting for business hours. Whether you need help interpreting an error code from the /v1/audio/speech endpoint or want to verify a character count, our team is ready to assist.
- No automated routing or tiered support levels
- Detailed technical context included in every message
No Phone Support
We do not offer phone support. This decision aligns with our focus on asynchronous, documented communication that indie developers prefer for tracking issues. Phone calls can be difficult to reference later when debugging API integrations, whereas an email thread provides a permanent record of the solution and the context surrounding your fintech notification workflow.
Response Times
For critical billing or API outage issues affecting your notification service, we often reply sooner. Since we are a small, independent team, response times may vary slightly depending on the volume of support requests, but we prioritize clarity and accuracy over speed.
Network Independence
VoxEdge operates as an independent storefront for the same underlying text-to-speech API. While our request shape mirrors the OpenAI speech endpoint, we are not affiliated with OpenAI, ElevenLabs, Google, Amazon, or Microsoft. We do not use their infrastructure or branding, ensuring you connect directly to our dedicated endpoints.
Not Affiliated with OpenAI
Our API compatibility is a convenience feature, not an endorsement. We are a separate entity with distinct keys, billing, and rate limits. When you change the base_url to https://api.idrok.top/v1, you are using our independent service, not OpenAI’s infrastructure.
Independent API Provider
We control the entire stack, from voice licensing to server deployment. This independence allows us to tailor our pricing and limits specifically for indie developers in fintech, without relying on third-party platform changes or policies that affect larger providers.
Transparent Operations
All operations are straightforward: you send text, we return audio. There is no SLA or data-center choice. We maintain clear records of your requests for billing purposes, and our voice sources are openly documented under CC BY 4.0.
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. For live voice interactions requiring immediate partial audio, consider combining multiple short requests or using a different streaming solution.
23 languages
Any voice speaks any of these languages.
